Dynamic Reconstruction of Ultrasound-Derived Flow Fields With Physics-Informed Neural Fields

• URL: http://arxiv.org/abs/2511.01804v1
• Date: Mon, 03 Nov 2025 18:05:11 GMT
• Title: Dynamic Reconstruction of Ultrasound-Derived Flow Fields With Physics-Informed Neural Fields
• Authors: Viraj Patel, Lisa Kreusser, Katharine Fraser,
• Abstract summary: We present a physics-informed neural field model for estimating blood flow from sparse and noisy ultrasound data.<n>This model achieves consistently low mean squared error in denoising and inpainting both synthetic and real datasets.<n>We adapt methods that have proven effective in other imaging modalities to address the specific challenge of ultrasound-based flow reconstruction.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Blood flow is sensitive to disease and provides insight into cardiac function, making flow field analysis valuable for diagnosis. However, while safer than radiation-based imaging and more suitable for patients with medical implants, ultrasound suffers from attenuation with depth, limiting the quality of the image. Despite advances in echocardiographic particle image velocimetry (EchoPIV), accurately measuring blood velocity remains challenging due to the technique's limitations and the complexity of blood flow dynamics. Physics-informed machine learning can enhance accuracy and robustness, particularly in scenarios where noisy or incomplete data challenge purely data-driven approaches. We present a physics-informed neural field model with multi-scale Fourier Feature encoding for estimating blood flow from sparse and noisy ultrasound data without requiring ground truth supervision. We demonstrate that this model achieves consistently low mean squared error in denoising and inpainting both synthetic and real datasets, verified against reference flow fields and ground truth flow rate measurements. While physics-informed neural fields have been widely used to reconstruct medical images, applications to medical flow reconstruction are mostly prominent in Flow MRI. In this work, we adapt methods that have proven effective in other imaging modalities to address the specific challenge of ultrasound-based flow reconstruction.

Related papers

• Graph Deep Learning for Intracranial Aneurysm Blood Flow Simulation and Risk Assessment [2.759923839023361]
  Intracranial aneurysms are a major cause of neurological morbidity and mortality worldwide.<n> Conventional computational fluid dynamics simulations provide accurate insights but are prohibitively slow and require specialized expertise.<n>We present a graph neural network surrogate model that bridges this gap by reproducing full-field hemodynamics directly from vascular geometries.
  arXiv  Detail & Related papers  (2025-12-09T18:31:35Z)
• Fluid Dynamics and Domain Reconstruction from Noisy Flow Images Using Physics-Informed Neural Networks and Quasi-Conformal Mapping [11.456430320090218]
  Blood flow imaging provides important information for hemodynamic behavior within the vascular system.<n>However, obtaining high-quality flow images remains a significant challenge.<n>We address the problem of denoising flow images that may suffer from artifacts due to short acquisition times or device-induced errors.
  arXiv  Detail & Related papers  (2025-08-15T04:49:07Z)
• Ultrasound Lung Aeration Map via Physics-Aware Neural Operators [78.6077820217471]
  Lung ultrasound is a growing modality in clinics for diagnosing acute and chronic lung diseases.<n>It is complicated by complex reverberations from the pleural interface caused by the inability of ultrasound to penetrate air.<n>We propose LUNA, an AI model that directly reconstructs lung aeration maps from RF data.
  arXiv  Detail & Related papers  (2025-01-02T09:24:34Z)
• Motion Artifact Removal in Pixel-Frequency Domain via Alternate Masks and Diffusion Model [58.694932010573346]
  Motion artifacts present in magnetic resonance imaging (MRI) can seriously interfere with clinical diagnosis.<n>We propose a novel unsupervised purification method which leverages pixel-frequency information of noisy MRI images to guide a pre-trained diffusion model to recover clean MRI images.
  arXiv  Detail & Related papers  (2024-12-10T15:25:18Z)
• CathFlow: Self-Supervised Segmentation of Catheters in Interventional Ultrasound Using Optical Flow and Transformers [66.15847237150909]
  We introduce a self-supervised deep learning architecture to segment catheters in longitudinal ultrasound images. The network architecture builds upon AiAReSeg, a segmentation transformer built with the Attention in Attention mechanism. We validated our model on a test dataset, consisting of unseen synthetic data and images collected from silicon aorta phantoms.
  arXiv  Detail & Related papers  (2024-03-21T15:13:36Z)
• Real-Time Model-Based Quantitative Ultrasound and Radar [65.268245109828]
  We propose a neural network based on the physical model of wave propagation, which defines the relationship between the received signals and physical properties. Our network can reconstruct multiple physical properties in less than one second for complex and realistic scenarios.
  arXiv  Detail & Related papers  (2024-02-16T09:09:16Z)
• Physics-informed neural networks for blood flow inverse problems [2.5543665891116163]
  Physics-informed neural networks (PINNs) have emerged as a powerful tool for solving inverse problems. In this work, we use the PINNs methodology for estimating reduced-order model parameters and the full velocity field from scatter 2D noisy measurements in the ascending aorta.
  arXiv  Detail & Related papers  (2023-08-02T04:04:49Z)
• On Sensitivity and Robustness of Normalization Schemes to Input Distribution Shifts in Automatic MR Image Diagnosis [58.634791552376235]
  Deep Learning (DL) models have achieved state-of-the-art performance in diagnosing multiple diseases using reconstructed images as input. DL models are sensitive to varying artifacts as it leads to changes in the input data distribution between the training and testing phases. We propose to use other normalization techniques, such as Group Normalization and Layer Normalization, to inject robustness into model performance against varying image artifacts.
  arXiv  Detail & Related papers  (2023-06-23T03:09:03Z)
• Data and Physics Driven Learning Models for Fast MRI -- Fundamentals and Methodologies from CNN, GAN to Attention and Transformers [72.047680167969]
  This article aims to introduce the deep learning based data driven techniques for fast MRI including convolutional neural network and generative adversarial network based methods. We will detail the research in coupling physics and data driven models for MRI acceleration. Finally, we will demonstrate through a few clinical applications, explain the importance of data harmonisation and explainable models for such fast MRI techniques in multicentre and multi-scanner studies.
  arXiv  Detail & Related papers  (2022-04-01T22:48:08Z)
• High-Precision Inversion of Dynamic Radiography Using Hydrodynamic Features [3.3441584690770134]
  We propose a fundamentally new approach to reconstructing density from a temporal sequence of radiographs. We use only the robust features identifiable in radiographs to determine the density fields from a dynamic sequence of radiographs. Next, we seek to further enhance the hydrodynamic consistency of the ML-based density reconstruction through a process of parameter estimation and projection onto a hydrodynamic manifold.
  arXiv  Detail & Related papers  (2021-12-02T22:36:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.